Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning
Guodong Liu (Huazhong University of Science and Technology), Tongling Wang (Huazhong University of Science and Technology), Shuoxi Zhang (Huazhong University of Science and Technology), Kun He (Huazhong University of Science and Technology)*
The 34th British Machine Vision Conference
Abstract
Model-Agnostic Meta-Learning (MAML) is a famous few-shot learning method that has inspired many follow-up efforts, such as ANIL and BOIL. However, as an inductive method, MAML is unable to fully utilize the information of query set, limiting its potential of gaining higher generality. To address this issue, we propose a simple yet effective method that generates pseudo-labels adaptively and could boost the performance of the MAML family. The proposed methods, dubbed Generative Pseudo-label based MAML (GP-MAML), GP-ANIL and GP-BOIL (when combined with MAML, ANIL and GP-BOIL respectively), leverage statistics of the query set to improve the performance on new tasks. Specifically, we adaptively add pseudo labels and pick samples from the query set, then re-train the model using the picked query samples together with the support set. The GP series can also use information from the pseudo query set to re-train the network during the meta-testing. While some transductive methods, such as Transductive Propagation Network (TPN), struggle to achieve this goal. Experiments show that all our methods, GP-MAML, GP-ANIL and GP-BOIL, can boost the performance of the corresponding model considerably, and achieve competitive performance as compared to the state-of-the-art baselines.Citation
@inproceedings{Liu_2023_BMVC,
author = {Guodong Liu and Tongling Wang and Shuoxi Zhang and Kun He},
title = {Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0292.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by